Official code for the experimental section of the paper:

A Reinforcement Learning Approach in Multi-Phase Second-Price Auction Design

Rui Ai, Boxiang Lyu, Zhaoran Wang, Zhuoran Yang, Michael I. Jordan [arXiv]

We implement the following algorithms under different market noise distributions:

Contextual Bandit Setting:

• CLUB
• SCORP
• NPAC-S

MDP Setting:

• CLUB
• NPAC-S

If you use this codebase, or otherwise found our work valuable, please cite:

@article{ai2022reinforcement,
  title={A reinforcement learning approach in multi-phase second-price auction design},
  author={Ai, Rui and Lyu, Boxiang and Wang, Zhaoran and Yang, Zhuoran and Jordan, Michael I},
  journal={arXiv preprint arXiv:2210.10278},
  year={2022}
}